Distributed Machine Learning for Multiuser Mobile Edge Computing Systems

Guo, Y. Jay; Zhao, Rui; Lai, Shiwei; Fan, Lisheng; Lei, Xianfu; Karagiannidis, George K.

doi:10.1109/jstsp.2022.3140660

Cited by 95 publications

(31 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, the cloud computing-based network settings are increasingly being replaced by processing at the network's edge, i.e., edge computing, which allows for the implementation of ML algorithms to make the best use of the data these devices produce. The concept of centralized ML is no longer dominant [23]. This trend reversal has as its cornerstone the introduction of distributed learning algo-rithms [3].…”

Section: Distributed Machine Learning Algorithmsmentioning

confidence: 99%

Overview of Distributed Machine Learning Techniques for 6G Networks

2022

View full text Add to dashboard Cite

The main goal of this paper is to survey the influential research of distributed learning technologies playing a key role in the 6G world. Upcoming 6G technology is expected to create an intelligent, highly scalable, dynamic, and programable wireless communication network able to serve many heterogeneous wireless devices. Various machine learning (ML) techniques are expected to be deployed over the intelligent 6G wireless network that provide solutions to highly complex networking problems. In order to do this, various 6G nodes and devices are expected to generate tons of data through external sensors, and data analysis will be needed. With such massive and distributed data, and various innovations in computing hardware, distributed ML techniques are expected to play an important role in 6G. Though they have several advantages over the centralized ML techniques, implementing the distributed ML algorithms over resource-constrained wireless environments can be challenging. Therefore, it is important to select a proper ML algorithm based upon the characteristics of the wireless environment and the resource requirements of the learning process. In this work, we survey the recently introduced distributed ML techniques with their characteristics and possible benefits by focusing our attention on the most influential papers in the area. We finally give our perspective on the main challenges and advantages for telecommunication networks, along with the main scenarios that could eventuate.

show abstract

Section: Distributed Machine Learning Algorithmsmentioning

confidence: 99%

Overview of Distributed Machine Learning Techniques for 6G Networks

2022

View full text Add to dashboard Cite

show abstract

“…As said earlier, the local datasets results of the hidden layer should be concatenated to get the global results; the concatenate result is described in (11):…”

Section: ∨ ( )mentioning

confidence: 99%

“…In (11), the replica data input is represented as X i , is the reconstructed output values of replica data, j-th replica data's local code is denoted as H jk , concatenate function is defined as concat (.). The global input matrix is defined as concat (H jk ), and the reconstructed global input matrix is defined as H jk .…”

Section: ∨ ( )mentioning

confidence: 99%

“…Then, the parallel knowledge analysis approaches are utilized to resolve the problem with maximum performance using multi-computer devices. Therefore, machine learning techniques [10,11] are applied to investigate the distributed dataset for exploring the results. Among the various techniques, clustering is an effective approach that analyses similar data to identify the unknown results.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Privacy protection based distributed clustering with deep learning algorithm for distributed data mining

Mahmood¹,

Naser²,

Khalil

2022

EEJET

View full text Add to dashboard Cite

Distributed Data Mining (DDM) is vital in various applications for processing large volumes of data. The datasets are saved in the local databases and operated by local communities, but it provides the solution locally and globally. However, the datasets are stored in a distributed manner which affects the scalability and reliability issues. In addition, locally stored data is influenced by security and privacy challenges. In addition, the third party may access the DDM, which causes authorization issues. Therefore, the DDM process fuses sensor data from different sources to improve knowledge discovery. During this process, the DDM faces several issues such as security concerns, privacy restrictions, technical barriers, and trust issues. To address these issues, distributed data mining (DDM) should be improved to handle homogeneous and heterogeneous data. This work uses the privacy protection-based distributed clustering (PPDC) algorithm to handle the privacy and security challenges while analyzing the distributed data. The clustering algorithm generates the semi-trusted third parties to form the cluster, which protects the data from unauthorized users. The semi-trusted party protect the locally analyzed solution by creating the random vector-based trusted process. Further, the process uses the optimized deep learning approach and clustering to improve the heterogeneous data analysis. Then the effectiveness of the introduced PPDC method is compared with existing methods, and the PPDC algorithm ensures the 0.202 error rate, 0.95 % of accuracy and manages the data security.

show abstract

“…Currently, massive data communication and computing pose a severe challenge to the existing wireless network architecture [1][2][3][4]. At present, the traditional communication network still adopts the communication-centric architecture, which is difficult to support the increasing application demand of massive data computing [5][6][7][8].…”

Section: Introductionmentioning

confidence: 99%

An Overview on Active Transmission Techniques for Wireless Scalable Networks

Tang

Lai

Zhang

et al. 2022

EAI Endorsed Scal Inf Syst

Self Cite

View full text Add to dashboard Cite

Currently, massive data communication and computing pose a severe challenge on existing wireless network architecture, from various aspects such as data rate, latency, energy consumption and pricing. Hence, it is of vital importance to investigate active wireless transmission for wireless networks. To this end, we first overview the data rate of wireless active transmission. We then overview the latency of wireless active transmission, which is particularly important for the applications of monitoring services. We further overview the spectral efficiency of the active transmission, which is particularly important for the battery-limited Internet of Things (IoT) networks. After these overviews, we give several critical challenges on the active transmission, and we finally present feasible solutions to meet these challenges. The work in this paper can serve as an important reference to the wireless networks and IoT networks.

show abstract

Distributed Machine Learning for Multiuser Mobile Edge Computing Systems

Cited by 95 publications

References 33 publications

Overview of Distributed Machine Learning Techniques for 6G Networks

Overview of Distributed Machine Learning Techniques for 6G Networks

Privacy protection based distributed clustering with deep learning algorithm for distributed data mining

An Overview on Active Transmission Techniques for Wireless Scalable Networks

Contact Info

Product

Resources

About